Frequent travelers often have the ability to predict the optimal time to purchase airline tickets in order to secure the best price. In order to maximize revenue, airlines frequently adjust their ticket pricing, which may result in higher prices during periods of high demand. To determine the airfare for a given route, data was collected over a specific period of time, which included various parameters such as flight schedules, airlines, and other relevant factors. Machine learning models were then employed to extract useful features from this data. Understanding the drivers of airfare price fluctuations is crucial in developing a mechanism that assists consumers and revenue management systems in making informed decisions about ticket purchases, considering the influence of various distinct factors on the cost of a plane ticket. The study aims to identify these key factors and their connection to price changes. By incorporating various powerful machine learning techniques such as Random Forest Regressor, Decision Tree Regressor, Linear Regression, and KNeighbors Regressor, Extra Trees Regressor, Bagging Regressor, this study aims to build a highly reliable and accurate flight fare prediction model that can efficiently handle diverse types of data, thus contributing to the advancement of more efficient and dependable airline ticket pricing systems.
Leveraging Machine Learning Techniques to Estimate Airline Ticket Pricing
2023-11-23
3876251 byte
Conference paper
Electronic Resource
English